Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 139 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.6690. Min Act: -0.0001

Data Index: 1167405 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.7268. Min Act: -0.0001

Data Index: 1267202 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.6533. Min Act: -0.0001

Data Index: 126197 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.5502. Min Act: -0.0001

Data Index: 31331 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.6219. Min Act: -0.0001

Data Index: 1279162 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.5230. Min Act: -0.0001

Data Index: 81450 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.5782. Min Act: -0.0001

Data Index: 81879 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.5753. Min Act: -0.0001

Data Index: 919159 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.4113. Min Act: -0.0001

Data Index: 386307 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.3936. Min Act: -0.0001

Data Index: 1043080 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.4288. Min Act: -0.0001

Data Index: 269113 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.4435. Min Act: -0.0001

Data Index: 264258 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.3993. Min Act: -0.0001

Data Index: 561915 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.4400. Min Act: -0.0001

Data Index: 643548 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.4253. Min Act: -0.0001

Data Index: 1059526 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.4066. Min Act: -0.0001

Data Index: 475462 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.4022. Min Act: -0.0001

Data Index: 932949 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.3425. Min Act: -0.0001

Data Index: 59823 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.3509. Min Act: -0.0001

Data Index: 281199 (C4 (Web Text))

Max Activating Token Index: 433

Text #19

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.2743. Min Act: -0.0001

Data Index: 490297 (C4 (Web Text))

Max Activating Token Index: 917